English
Related papers

Related papers: Specification Self-Correction: Mitigating In-Conte…

200 papers

There is a growing interest in cost-effective self-supervised fine-tuning (SSFT) of self-supervised learning (SSL)-based speech models to obtain task-specific representations. These task-specific representations are used for robust…

Computation and Language · Computer Science 2024-03-12 Amit Meghanani , Thomas Hain

Classical computability theory tells us that self-modifying code (SMC) on a deterministic universal Turing machine can be simulated by non-SMC code on the same model. That abstraction, however, omits the external timing inputs, concurrency,…

Cryptography and Security · Computer Science 2026-04-15 Gregory Morse , Tamás Kozsik

Small Language Models (SLMs) are increasingly being deployed in resource-constrained environments, yet their behavioral robustness to data contamination during instruction tuning remains poorly understood. We systematically investigate the…

Computation and Language · Computer Science 2025-11-11 Nicy Scaria , Silvester John Joseph Kennedy , Deepak Subramani

Chinese Spelling Correction (CSC) aims to detect and correct erroneous tokens in sentences. Traditional CSC focuses on equal length correction and uses pretrained language models (PLMs). While Large Language Models (LLMs) have shown…

Computation and Language · Computer Science 2025-08-12 Junhong Liang , Yu Zhou

Developers often struggle to specify correct training labels and rewards. Perhaps they don't need to. We propose recontextualization, which reduces how often language models "game" training signals, performing misbehaviors those signals…

Self-correction has achieved impressive results in enhancing the style and security of the generated output from large language models (LLMs). However, recent studies suggest that self-correction might be limited or even counterproductive…

Computation and Language · Computer Science 2024-06-18 Che Zhang , Zhenyang Xiao , Chengcheng Han , Yixin Lian , Yuejian Fang

The use of language is subject to variation over time as well as across social groups and knowledge domains, leading to differences even in the monolingual scenario. Such variation in word usage is often called lexical semantic change…

Computation and Language · Computer Science 2021-02-02 Maurício Gruppi , Sibel Adalı , Pin-Yu Chen

Existing refinement methods in LLM-based Text-to-SQL systems exhibit limited effectiveness. They often introduce new errors during the self-correction process and fail to detect and correct semantic inaccuracies. To address these gaps, we…

Artificial Intelligence · Computer Science 2025-05-22 Jikai Chen , Leilei Gan , Ziyu Zhao , Zechuan Wang , Dong Wang , Chenyi Zhuang

With the rapid development of Large Language Models (LLMs), Natural Language Explanations (NLEs) have become increasingly important for understanding model predictions. However, these explanations often fail to faithfully represent the…

Computation and Language · Computer Science 2025-09-09 Yingming Wang , Pepa Atanasova

Large language models have driven major advances in Text-to-SQL generation. However, they suffer from high computational cost, long latency, and data privacy concerns, which make them impractical for many real-world applications. A natural…

A sequence-to-sequence learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spelling errors as input and outputs the corrected one.…

Computation and Language · Computer Science 2021-06-02 Chong Li , Cenyuan Zhang , Xiaoqing Zheng , Xuanjing Huang

Recently, Test-Time Scaling (TTS) has gained increasing attention for improving LLM reasoning performance at test time without retraining the model. A notable TTS technique is Self-Consistency (SC), which generates multiple reasoning chains…

Computation and Language · Computer Science 2025-09-18 Colin Hong , Xu Guo , Anand Chaanan Singh , Esha Choukse , Dmitrii Ustiugov

Recent research in retrieval-augmented generation (RAG) has concentrated on retrieving useful information from candidate documents. However, numerous methodologies frequently neglect the calibration capabilities of large language models…

Computation and Language · Computer Science 2025-06-23 Guanhua Chen , Yutong Yao , Lidia S. Chao , Xuebo Liu , Derek F. Wong

Reinforcement learning (RL) is a framework for solving sequential decision-making problems. In this work, we demonstrate that, surprisingly, RL emerges during the inference time of large language models (LLMs), a phenomenon we term…

Machine Learning · Computer Science 2026-04-28 Kefan Song , Amir Moeini , Peng Wang , Lei Gong , Rohan Chandra , Shangtong Zhang , Yanjun Qi

Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs), where LLMs refine their solutions using self-generated critiques that pinpoint the errors. This work explores whether…

Computation and Language · Computer Science 2024-06-07 Yunxiang Zhang , Muhammad Khalifa , Lajanugen Logeswaran , Jaekyeom Kim , Moontae Lee , Honglak Lee , Lu Wang

Language models are often trained to maximize the likelihood of the next token given past tokens in the training dataset. However, during inference time, they are utilized differently, generating text sequentially and auto-regressively by…

Machine Learning · Computer Science 2025-01-22 Zhepeng Cen , Yao Liu , Siliang Zeng , Pratik Chaudhari , Huzefa Rangwala , George Karypis , Rasool Fakoor

Scaling test-time computation--generating and analyzing multiple or sequential outputs for a single input--has become a promising strategy for improving the reliability and quality of large language models (LLMs), as evidenced by advances…

Computation and Language · Computer Science 2025-06-03 Sungjae Lee , Hoyoung Kim , Jeongyeon Hwang , Eunhyeok Park , Jungseul Ok

Text-to-SQL aims to convert natural language questions into executable SQL queries. While previous approaches, such as skeleton-masked selection, have demonstrated strong performance by retrieving similar training examples to guide large…

Computation and Language · Computer Science 2025-10-01 Jimin Lee , Ingeol Baek , Byeongjeong Kim , Hyunkyung Bae , Hwanhee Lee

Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to…

Large Language Models (LLMs) have exhibited remarkable performance across various natural language processing (NLP) tasks. However, fine-tuning these models often necessitates substantial supervision, which can be expensive and…

Computation and Language · Computer Science 2023-05-25 Jing-Cheng Pang , Pengyuan Wang , Kaiyuan Li , Xiong-Hui Chen , Jiacheng Xu , Zongzhang Zhang , Yang Yu